Brian Model @brain_model

Founder at Thunder Compute (YC S24) | Fan of C++ | Previously HFT @ Citadel Securities thundercompute.com Making GPUs go brrr @ → Joined March 2020

Tweets

53
Followers

161
Following

356
Likes

1K

Weave Robotics @weaverobotics

4 weeks ago

People want a robot that can fold their laundry, and we’re going to give it to them

22 48 350 88K 85

Download Video

Probably the coolest implementation of a circular buffer I've ever seen: github.com/gnuradio/gnura… Essentially they mmap 2 contiguous regions of virtual memory to alias the same data. Then they can call memcpy 1 time and have the hardware automatically handle the wraparound logic.

0 0 6 541 8

Brian Model @brain_model

3 months ago

real

0 0 0 55 0

Download Image

Brian Model @brain_model

3 months ago

"How to update cuda drivers"

0 0 2 84 0

Download Image

Brian Model @brain_model

4 months ago

"Small" change to optimize serialization got a little out of hand😮‍💨

0 0 2 103 0

Download Image

Brian Model @brain_model

5 months ago

Why is it that PyYAML is always an issue with trying to install python requirements? Who decided they needed to use c extensions for a yaml parser??

0 0 1 86 0

Carl Peterson @Carl_petey

5 months ago

We're seeing a massive spike in demand at @ThunderCompute. New record highs every hour. Please bear with us for any service interruptions, our team is working hard to keep everything online!!

1 3 13 651 0

Brian Model @brain_model

6 months ago

Not shown: me pacing around the office trying to understand cusolver docs

Thunder Compute @ThunderCompute

6 months ago

Not shown: me pacing around the office trying to understand cusolver docs

1 2 9 528 0

Download Image

0 0 3 225 0

Thunder Compute @ThunderCompute

6 months ago

We’ve been absolutely cheffing and have a ton of updates for you: Performance - Improved performance for large models: 4-6x faster data transfers - ~75% faster initial GPU connection - Expanded compatibility with data science and ML workloads - MUCH faster template launch times…

1 3 8 372 0

Download Image

Carl Peterson @Carl_petey

6 months ago

I'll be repping @ThunderCompute at @NVIDIAGTC. If you're looking for the cheapest GPUs, DM me.

0 3 4 283 0

Carl Peterson @Carl_petey

6 months ago

Apple intelligence sucks. Can't even run nvidia-smi. Apple uses weak, small LLMs. Big LLMs are better. Thankfully, I got 80GB of VRAM on my iPhone with @ThunderCompute nvidia-smi ✅

1 3 7 3K 2

Download Video

Brian Model @brain_model

6 months ago

Just tried opening docs.nvidia.com/cuda/cublas/ on my phone @nvidia

0 0 1 78 0

Download Image

Carl Peterson @Carl_petey

6 months ago

We just got our VS Code extension published! Our team has been using this nonstop for internal development. It truly feels like your computer has GPUs attached. If you use @code or @Cursor this is the simplest way to use cloud GPUs. And it was already the cheapest.

1 3 14 315 1

Download Image

Jack @jackowfish

6 months ago

Spent the last couple days putting together a VSCode extension for @ThunderCompute - actually the fastest way to get a GPU cloud instance to build with LLM's in cursor. 5 clicks and a 30 second wait and you're building with server-grade GPU's right in your editor.

3 5 6 540 0

Download Video

Thunder Compute @ThunderCompute

7 months ago

Our founding engineer @jackowfish monitoring google cloud as we have 70 people test Thunder Compute live.

2 2 11 568 0

Download Image

Carl Peterson @Carl_petey

7 months ago

Thank you Pace University Data Science for inviting @ThunderCompute to lead a workshop about using cloud GPUs for deep learning. We love to hear how students are using our GPUs for their projects.

0 3 11 347 1

Download Image

Jack @jackowfish

7 months ago

🚢Just shipped an update to our CLI tool that allows you change your @ThunderCompute instance's properties while stopped. No need to re-create an instance you've spent months working on because you need more vCPUs!